© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 60463
    Prev
    Next
    INDEX
    Explanations

    faith traditions and associated terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.3-70B-IT @ 50-resid-post-gf
    Configuration
    Goodfire/Llama-3.3-70B-Instruct-SAE-l50/Llama-3.3-70B-Instruct-SAE-l50.pt
    Prompts (Dashboard)
    10,000 prompts, 128 tokens each
    Dataset (Dashboard)
    lmsys/lmsys-chat-1m
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lutheran
    -0.11
     LDS
    -0.11
     Catholic
    -0.11
     Catholics
    -0.11
     jung
    -0.10
    anian
    -0.10
    undo
    -0.10
    oyer
    -0.09
    assing
    -0.09
     Baptist
    -0.09
    POSITIVE LOGITS
    ism
    0.22
    -Muslim
    0.18
    -major
    0.17
    -Christian
    0.14
    isme
    0.14
    å¾Ĵ
    0.13
     faith
    0.13
    osate
    0.13
     tradition
    0.12
    ISM
    0.12
    Activations Density 0.040%

    No Known Activations